Nvidia has unveiled GeForce RTX 40 series graphics cards with 4X performance

Nvidia has unveiled GeForce RTX 40 series graphics cards with 4X performance ...

Today, Nvidia CEO Jensen Huang showed off the company's latest graphics cards, including the consumer-focused GeForce RTX 40 Series of graphics processing units (GPUs).

The RTX 4090 GPU is the series' flagship chip, offering up to four times the performance of its predecessor.

Huang promised enormous generational leaps in performance and efficiency, describing the new age of real-time ray tracing and neural rendering, which relies on artificial intelligence to create pixels.

"Our new Ada Lovelace architecture elevates RTX ray tracing and neural rendering to the next level," said Huang during the company's fall GTC event. "Ada is paving the path for game designers who want fully simulated worlds," said the author.

Huang showed off a video dubbed Racer X that showed toy cars racing around a room with incredible shadows and lighting. Ada Lovelace is a huge improvement over the previous generation, according to Huang.

"Ada, right off the bat, improves performance on today's games," said Matt Wuebbling, the global head of Nvidia GeForce marketing, in a press conference. "This is our biggest leap ever," says the latter.

He described the Racer X video as a 4X improvement of the GPU's simulation capabilities.

“Racer X is a simulation,” Huang said. “Racer X is running on a single GPU.”

DLSS 3 generates entire frames for more responsive game play.

Huang also unveiled Nvidia DLSS 3, the next generation in the company's Deep Learning Super Sampling neural-graphics technology for games and creative apps.

The AI-powered technology can generate whole frames for significantly faster gameplay. It can overcome CPU performance limitations in games by allowing the GPU to generate whole frames independently. In a moving scene, the AI can anticipate what kinds of pixels to fill in faster.

Nvidia said the technology is coming to the world's most popular game engines, such as Unity and Unreal Engine, and has received support from many of the world's leading game developers. Over 35 games and apps are expected soon.

  • Additionally, the RTX 40 Series GPUs feature a range of new technological innovations, including: Streaming multiprocessors with up to 83 teraflops of shader power — 2x over the previous generation.
  • Third-generation RT Cores with up to 191 effective ray-tracing teraflops — 2.8x over the previous generation.
  • Fourth-generation Tensor Cores with up to 1.32 Tensor petaflops — 5x over the previous generation using FP8 acceleration.
  • Shader Execution Reordering (SER) that improves execution efficiency by rescheduling shading workloads on the fly to better utilize the GPU’s resources. As significant an innovation as out-of-order execution was for CPUs, SER improves ray-tracing performance up to three times and in-game frame rates by up to 25%.
  • Ada Optical Flow Accelerator with 2x faster performance allows DLSS 3 to predict movement in a scene, enabling the neural network to boost frame rates while maintaining image quality.
  • Architectural improvements tightly coupled with custom TSMC 4N process technology results in an up to 2x leap in power efficiency.
  • Dual Nvidia Encoders (NVENC) cut export times by up to half and feature AV1 support. The NVENC AV1 encode is being adopted by OBS, Blackmagic Design DaVinci Resolve, Discord and more.

Experience new ray-tracing in immersive games

The ability to see ray-traced scenes with physically correct lighting in real time has been considered the holy grail of graphics for decades. At the same time, geometric complexity of environments and objects has continued to increase as 3D games and graphics strive to provide the most accurate representations of the real world, according to Nvidia.

Achieving physically accurate graphics requires enormous computational power. Modern ray-traced games like Cyberpunk 2077 perform over 600 ray-tracing calculations for each pixel just to determine lighting — an increase of 16x over the first ray-traced games introduced four years ago.

The new third-generation RT Cores have been enhanced to provide 2x faster ray-triangle intersection testing, and include two significant new hardware units: An Opacity Micromap Engine speeds up alpha-test geometry a factor of 2x, and a Micro-Mesh Engine generates micro-meshes on the fly to create additional geometry.

Huang said Nvidia engineers encouraged technology on every level.

Encoders for RTX Remix and AV1

Nvidia Studio creators benefit from the RTX 40 Series GPUs and DLSS 3's improvements. 3D artists can render fully ray-traced environments with precise physics and realistic materials, and they can see the changes in real time, without proxies.

Improved GPU performance and the addition of new dual, eighth-generation AV1 encoders give video editing and live streaming a boost. Three new features are now available for partners, including Face Expression Estimation, Eye Contact, and quality improvements to Virtual Background.

Nvidia RTX Remix is a freeware game creation engine that allows gamers to quickly add RTX remasters using powerful AI tools. RTX Remix is also available for purchase in Nvidia Omniverse.

Nvidia Lightspeed Studios has used RTX Remix to recreate Valve's video game Portal, which is widely regarded as one of the greatest video games of all time. Portal with RTX will be released as free, official downloadable content in November, just in time for Portal's 15th anniversary.

Huang said. "We have developed an Omniverse application called RTX Remix."

The GeForce RTX 4090 and 4080 GPUs

The RTX 4090 is the world's fastest gaming GPU, with astonishing power, acoustics, and temperature characteristics. In full ray-traced games, the RTX 4090 with DLSS 3 is up to 4x faster than the previous generation's RTX 3090 Ti with DLSS 2.

It can be up to two times faster in today's games while maintaining the same 450W power consumption. It has 76 billion transistors, 16,384 CUDA cores, 24GB of high-speed Micron GDDR6X memory, and consistently delivers over 100 frames per second at 4K-resolution gaming.

The RTX 4080 is now available in two configurations, with 9,728 CUDA cores and 16GB of high-speed Micron GDDR6X memory, and with DLSS 3 it's 2x as fast in today's games as the GeForce RTX 3080 Ti, which is more powerful at lower power.

The RTX 4080 12GB has 7,680 CUDA cores and 12GB of Micron GDDR6X memory, and with DLSS 3, is faster than the previous-generation flagship GPU, the RTX 3090 Ti. Both RTX 4080 configurations will be available in November, starting at $1,200 and $900.

Where can I buy?

The GeForce RTX 4090 and 4080 GPUs will be available as custom boards from leading add-in card providers, such as Asus, Colorful, Gainward, Galaxy, GIGABYTE, Innovision 3D, MSI, Palit, PNY, and Zotac.

Nvidia has also produced the RTX 4090 and the RTX 4080 (16GB) directly in limited Founders Editions for Nvidia enthusiasts who want the Nvidia in-house design.

The GeForce RTX 40 Series GPUs will be used in gaming systems built by Acer, Alienware, ASUS, Dell, HP, Lenovo, and MSI, among other companies, throughout the world. And remember, Huang always says, the more you buy, the more you save.

You may also like: